baseline_french_arabic_kabyle

This model is a fine-tuned version of facebook/mms-1b-all on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.1710
• Wer: 0.2150
• Bleu: {'bleu': 0.7181439137868495, 'precisions': [0.8172253641275157, 0.7521161678767487, 0.6893509005197631, 0.627738590180782], 'brevity_penalty': 1.0, 'length_ratio': 1.1180148357470858, 'translation_length': 31651, 'reference_length': 28310}
• Rouge: {'rouge1': 0.9290507331814231, 'rouge2': 0.877068996182836, 'rougeL': 0.928568135242265, 'rougeLsum': 0.9287057494850774}

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 0.001
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Wer	Bleu	Rouge
No log	1.0	250	0.3712	0.3582	{'bleu': 0.5278472486368768, 'precisions': [0.7013763071739614, 0.5807095738990907, 0.4798814405781802, 0.3971815053966159], 'brevity_penalty': 1.0, 'length_ratio': 1.1113034263511128, 'translation_length': 31461, 'reference_length': 28310}	{'rouge1': 0.798035129706152, 'rouge2': 0.6807351190104856, 'rougeL': 0.7973280825352558, 'rougeLsum': 0.7972372866654838}
3.1239	2.0	500	0.2901	0.3284	{'bleu': 0.5686667698587203, 'precisions': [0.7288755175983437, 0.6175807390165843, 0.5231727574750831, 0.4440574662603396], 'brevity_penalty': 1.0, 'length_ratio': 1.0919109855174849, 'translation_length': 30912, 'reference_length': 28310}	{'rouge1': 0.8199263751889682, 'rouge2': 0.7127543632096307, 'rougeL': 0.8196159785817028, 'rougeLsum': 0.8196976327747123}
3.1239	3.0	750	0.2537	0.3118	{'bleu': 0.5768981116684755, 'precisions': [0.7311131187887473, 0.624795174842241, 0.5331855780266751, 0.4547742142105504], 'brevity_penalty': 1.0, 'length_ratio': 1.1338396326386435, 'translation_length': 32099, 'reference_length': 28310}	{'rouge1': 0.8456804238564215, 'rouge2': 0.742156398000457, 'rougeL': 0.845238023896572, 'rougeLsum': 0.8454111108499825}
0.367	4.0	1000	0.2337	0.2939	{'bleu': 0.6106927898835819, 'precisions': [0.7545419774335437, 0.6563774232777738, 0.568943036427349, 0.4936115843270869], 'brevity_penalty': 1.0, 'length_ratio': 1.108230307311904, 'translation_length': 31374, 'reference_length': 28310}	{'rouge1': 0.8554005259136783, 'rouge2': 0.762584540157837, 'rougeL': 0.8551036554459432, 'rougeLsum': 0.8551353596303144}
0.367	5.0	1250	0.2236	0.2946	{'bleu': 0.6090635792059497, 'precisions': [0.7539327279703287, 0.6543072505384063, 0.5670512191130748, 0.49194200142619443], 'brevity_penalty': 1.0, 'length_ratio': 1.1047686329918756, 'translation_length': 31276, 'reference_length': 28310}	{'rouge1': 0.8544499817518096, 'rouge2': 0.7597219171391328, 'rougeL': 0.8541000510506045, 'rougeLsum': 0.8541447143331091}
0.3017	6.0	1500	0.2107	0.2864	{'bleu': 0.6179425731015586, 'precisions': [0.7583722987488942, 0.6622751097889219, 0.577074939564867, 0.5030826716487623], 'brevity_penalty': 1.0, 'length_ratio': 1.1180501589544332, 'translation_length': 31652, 'reference_length': 28310}	{'rouge1': 0.865116056368076, 'rouge2': 0.7751137390492029, 'rougeL': 0.8648706872525473, 'rougeLsum': 0.8649359646513785}
0.3017	7.0	1750	0.2072	0.2841	{'bleu': 0.6228222468169561, 'precisions': [0.7600405101750166, 0.6662290195521805, 0.5826771653543307, 0.509997658627956], 'brevity_penalty': 1.0, 'length_ratio': 1.1161073825503356, 'translation_length': 31597, 'reference_length': 28310}	{'rouge1': 0.8666732011440186, 'rouge2': 0.778223076136866, 'rougeL': 0.8664992087555933, 'rougeLsum': 0.866524028492358}
0.2708	8.0	2000	0.2015	0.2744	{'bleu': 0.6345228154503069, 'precisions': [0.7686110318140007, 0.677990822098111, 0.5955861510427212, 0.5222926943857177], 'brevity_penalty': 1.0, 'length_ratio': 1.1136347580360297, 'translation_length': 31527, 'reference_length': 28310}	{'rouge1': 0.872959202159738, 'rouge2': 0.7886390907566294, 'rougeL': 0.8727691499863385, 'rougeLsum': 0.8728460817248329}
0.2708	9.0	2250	0.2013	0.2741	{'bleu': 0.6371579696262013, 'precisions': [0.7706673465485372, 0.6794935984550461, 0.5982644830114886, 0.5260692657077971], 'brevity_penalty': 1.0, 'length_ratio': 1.1083716001412929, 'translation_length': 31378, 'reference_length': 28310}	{'rouge1': 0.8757241437485311, 'rouge2': 0.7924702626655357, 'rougeL': 0.8753634004687673, 'rougeLsum': 0.8754667555561163}
0.2517	10.0	2500	0.1977	0.2713	{'bleu': 0.6381295480524106, 'precisions': [0.7720851982350887, 0.6809556022359099, 0.5989218110331969, 0.5266004986123524], 'brevity_penalty': 1.0, 'length_ratio': 1.1127870010596963, 'translation_length': 31503, 'reference_length': 28310}	{'rouge1': 0.8788759882038476, 'rouge2': 0.7975561416453387, 'rougeL': 0.8784243123598028, 'rougeLsum': 0.8784939662361415}
0.2517	11.0	2750	0.1932	0.2739	{'bleu': 0.6359294235285533, 'precisions': [0.7704616166105784, 0.6787978064240439, 0.5967323441174086, 0.5240402709823109], 'brevity_penalty': 1.0, 'length_ratio': 1.11261038502296, 'translation_length': 31498, 'reference_length': 28310}	{'rouge1': 0.8747640289347568, 'rouge2': 0.7913291314760371, 'rougeL': 0.8744497060038865, 'rougeLsum': 0.8744501320279807}
0.2356	12.0	3000	0.1920	0.2710	{'bleu': 0.6385111246615954, 'precisions': [0.7720509086304059, 0.6815761448349308, 0.5997414559263149, 0.526683221665183], 'brevity_penalty': 1.0, 'length_ratio': 1.115718827269516, 'translation_length': 31586, 'reference_length': 28310}	{'rouge1': 0.8800765036168291, 'rouge2': 0.7987744546839806, 'rougeL': 0.8796757702814868, 'rougeLsum': 0.8797885095592506}
0.2356	13.0	3250	0.1907	0.2689	{'bleu': 0.6417762089701201, 'precisions': [0.7711514846185333, 0.6833080478425008, 0.6042845107714526, 0.5327663134411601], 'brevity_penalty': 1.0, 'length_ratio': 1.1218297421405863, 'translation_length': 31759, 'reference_length': 28310}	{'rouge1': 0.8803421637314088, 'rouge2': 0.7996209590024225, 'rougeL': 0.8801310207196743, 'rougeLsum': 0.8801038848212641}
0.2275	14.0	3500	0.1894	0.2642	{'bleu': 0.6502108215089224, 'precisions': [0.7781164666285642, 0.6909680176650759, 0.6128051252939746, 0.5424901185770751], 'brevity_penalty': 1.0, 'length_ratio': 1.1124690921935712, 'translation_length': 31494, 'reference_length': 28310}	{'rouge1': 0.8833075472401195, 'rouge2': 0.8046199792704777, 'rougeL': 0.8829151700995652, 'rougeLsum': 0.883120491412912}
0.2275	15.0	3750	0.1911	0.2624	{'bleu': 0.6503528599575058, 'precisions': [0.7783497015820886, 0.6913383597040813, 0.6128447755184215, 0.5424757281553398], 'brevity_penalty': 1.0, 'length_ratio': 1.1185800070646414, 'translation_length': 31667, 'reference_length': 28310}	{'rouge1': 0.8856387650415731, 'rouge2': 0.8063881849941688, 'rougeL': 0.8851521760376129, 'rougeLsum': 0.8851458726706298}
0.214	16.0	4000	0.1846	0.2603	{'bleu': 0.6534288502142345, 'precisions': [0.7802785691674581, 0.6942571164903812, 0.6163260360287584, 0.5460252026045814], 'brevity_penalty': 1.0, 'length_ratio': 1.115860120098905, 'translation_length': 31590, 'reference_length': 28310}	{'rouge1': 0.8880086978536974, 'rouge2': 0.8112985132249853, 'rougeL': 0.8878328746101541, 'rougeLsum': 0.8877090579361144}
0.214	17.0	4250	0.1868	0.2610	{'bleu': 0.6536690869596536, 'precisions': [0.7811654625887146, 0.6947687912872701, 0.6161698320387164, 0.545943904051374], 'brevity_penalty': 1.0, 'length_ratio': 1.1098904980572235, 'translation_length': 31421, 'reference_length': 28310}	{'rouge1': 0.888159308242917, 'rouge2': 0.811950873463422, 'rougeL': 0.887753464518743, 'rougeLsum': 0.8878698167861805}
0.207	18.0	4500	0.1829	0.2581	{'bleu': 0.652485573986245, 'precisions': [0.7806400756739713, 0.694512173575038, 0.6157215769802676, 0.5429609276766172], 'brevity_penalty': 1.0, 'length_ratio': 1.1202755210173083, 'translation_length': 31715, 'reference_length': 28310}	{'rouge1': 0.8907788257397911, 'rouge2': 0.8147507183299365, 'rougeL': 0.890472472368699, 'rougeLsum': 0.8905229424253815}
0.207	19.0	4750	0.1842	0.2571	{'bleu': 0.6583765557380931, 'precisions': [0.7830087264449223, 0.6987097688926698, 0.6219954831424424, 0.5521369119985037], 'brevity_penalty': 1.0, 'length_ratio': 1.1172024019780995, 'translation_length': 31628, 'reference_length': 28310}	{'rouge1': 0.8915878831883641, 'rouge2': 0.8171822405845636, 'rougeL': 0.8910935738001518, 'rougeLsum': 0.8911412743527534}
0.1975	20.0	5000	0.1844	0.2568	{'bleu': 0.6604093848175463, 'precisions': [0.7844827586206896, 0.700774808075064, 0.6241100323624595, 0.5544085214208625], 'brevity_penalty': 1.0, 'length_ratio': 1.1145178382197103, 'translation_length': 31552, 'reference_length': 28310}	{'rouge1': 0.8926171158790939, 'rouge2': 0.8192477595804221, 'rougeL': 0.892376463579911, 'rougeLsum': 0.8924821198610968}
0.1975	21.0	5250	0.1809	0.2547	{'bleu': 0.6598272573376067, 'precisions': [0.7846076013406691, 0.7003190358029068, 0.6237396144228442, 0.5530561661132676], 'brevity_penalty': 1.0, 'length_ratio': 1.117131755563405, 'translation_length': 31626, 'reference_length': 28310}	{'rouge1': 0.8944660698210884, 'rouge2': 0.8206205838405253, 'rougeL': 0.8938214532051091, 'rougeLsum': 0.8939730953000364}
0.1926	22.0	5500	0.1826	0.2612	{'bleu': 0.6528953886577082, 'precisions': [0.781001047386295, 0.6942437079491652, 0.6156028368794326, 0.544390106272924], 'brevity_penalty': 1.0, 'length_ratio': 1.1129282938890852, 'translation_length': 31507, 'reference_length': 28310}	{'rouge1': 0.8897670120028007, 'rouge2': 0.8127417702375003, 'rougeL': 0.8892971240536487, 'rougeLsum': 0.8894543689738418}
0.1926	23.0	5750	0.1809	0.2502	{'bleu': 0.6630081593958751, 'precisions': [0.7858940480684535, 0.7036867333991259, 0.6273841961852861, 0.556927361336737], 'brevity_penalty': 1.0, 'length_ratio': 1.122854115153656, 'translation_length': 31788, 'reference_length': 28310}	{'rouge1': 0.8977033945594035, 'rouge2': 0.8260671944464686, 'rougeL': 0.897271052987286, 'rougeLsum': 0.8974223180640624}
0.1847	24.0	6000	0.1775	0.2518	{'bleu': 0.664617620951246, 'precisions': [0.7866210782917022, 0.7044123389301055, 0.6292466168450818, 0.5595952023988006], 'brevity_penalty': 1.0, 'length_ratio': 1.1157541504768633, 'translation_length': 31587, 'reference_length': 28310}	{'rouge1': 0.8942352732115131, 'rouge2': 0.8206491568800887, 'rougeL': 0.8940899979145857, 'rougeLsum': 0.8941264783022637}
0.1847	25.0	6250	0.1768	0.2514	{'bleu': 0.6673439251118893, 'precisions': [0.7881119766926341, 0.7069455294368298, 0.6326679059241898, 0.5626640419947506], 'brevity_penalty': 1.0, 'length_ratio': 1.1154362416107382, 'translation_length': 31578, 'reference_length': 28310}	{'rouge1': 0.8977994065582976, 'rouge2': 0.8262874637033506, 'rougeL': 0.8973576875505005, 'rougeLsum': 0.8974537363999516}
0.1763	26.0	6500	0.1740	0.2480	{'bleu': 0.6672953393422436, 'precisions': [0.7884288680551186, 0.7068382093761015, 0.6324837701370521, 0.5625232083178611], 'brevity_penalty': 1.0, 'length_ratio': 1.1227834687389615, 'translation_length': 31786, 'reference_length': 28310}	{'rouge1': 0.9006903529225825, 'rouge2': 0.8286153513232738, 'rougeL': 0.900322670952943, 'rougeLsum': 0.900331521820432}
0.1763	27.0	6750	0.1724	0.2447	{'bleu': 0.6758628746184816, 'precisions': [0.7934090981037702, 0.7146913711709794, 0.6419194571232378, 0.5732421417529395], 'brevity_penalty': 1.0, 'length_ratio': 1.1158247968915578, 'translation_length': 31589, 'reference_length': 28310}	{'rouge1': 0.9029447881778627, 'rouge2': 0.8348771955646912, 'rougeL': 0.9026641128550409, 'rougeLsum': 0.9028122513682509}
0.1719	28.0	7000	0.1731	0.2484	{'bleu': 0.673709029798307, 'precisions': [0.7917142494607283, 0.7125373559129073, 0.6393973756682326, 0.5711399304576638], 'brevity_penalty': 1.0, 'length_ratio': 1.113528788413988, 'translation_length': 31524, 'reference_length': 28310}	{'rouge1': 0.8998505378942794, 'rouge2': 0.8302960797570174, 'rougeL': 0.899459294724608, 'rougeLsum': 0.8995235565525509}
0.1719	29.0	7250	0.1704	0.2450	{'bleu': 0.6738148075843088, 'precisions': [0.7930618592693687, 0.7132533551671354, 0.6391084093211753, 0.5702125658389767], 'brevity_penalty': 1.0, 'length_ratio': 1.1129282938890852, 'translation_length': 31507, 'reference_length': 28310}	{'rouge1': 0.902133394303708, 'rouge2': 0.8326977810374041, 'rougeL': 0.9018069018405195, 'rougeLsum': 0.901922076249017}
0.1667	30.0	7500	0.1744	0.2480	{'bleu': 0.6690245090591024, 'precisions': [0.7890935469627199, 0.7083775185577943, 0.6341159443595722, 0.5652052369193495], 'brevity_penalty': 1.0, 'length_ratio': 1.1199576121511834, 'translation_length': 31706, 'reference_length': 28310}	{'rouge1': 0.8998246952773823, 'rouge2': 0.8286638662634496, 'rougeL': 0.8996990080190415, 'rougeLsum': 0.8996089688475792}
0.1667	31.0	7750	0.1801	0.2455	{'bleu': 0.673749871830189, 'precisions': [0.7918390550484793, 0.7129960703791554, 0.6393218154725947, 0.5708883805611316], 'brevity_penalty': 1.0, 'length_ratio': 1.1184387142352525, 'translation_length': 31663, 'reference_length': 28310}	{'rouge1': 0.9025928217012711, 'rouge2': 0.8347016284045304, 'rougeL': 0.9023447198920926, 'rougeLsum': 0.902186801811284}
0.1604	32.0	8000	0.1722	0.2419	{'bleu': 0.6767252228091671, 'precisions': [0.7942289498580889, 0.7161942461299216, 0.6427767505426482, 0.5736047703344824], 'brevity_penalty': 1.0, 'length_ratio': 1.1200989049805723, 'translation_length': 31710, 'reference_length': 28310}	{'rouge1': 0.9052736976492003, 'rouge2': 0.8378633942991702, 'rougeL': 0.9047662390848413, 'rougeLsum': 0.9047920343670606}
0.1604	33.0	8250	0.1740	0.2431	{'bleu': 0.6779607715238674, 'precisions': [0.7948620602379145, 0.7170119182746879, 0.6441314175008073, 0.5754739059208986], 'brevity_penalty': 1.0, 'length_ratio': 1.116495937831155, 'translation_length': 31608, 'reference_length': 28310}	{'rouge1': 0.9054577244056948, 'rouge2': 0.837859711436388, 'rougeL': 0.9051204447353197, 'rougeLsum': 0.905209132854425}
0.1535	34.0	8500	0.1728	0.2386	{'bleu': 0.6825833022854648, 'precisions': [0.7967382406649456, 0.7204543850984266, 0.6491776975531488, 0.5825549514382639], 'brevity_penalty': 1.0, 'length_ratio': 1.121935711762628, 'translation_length': 31762, 'reference_length': 28310}	{'rouge1': 0.9061642972611058, 'rouge2': 0.8381792497289737, 'rougeL': 0.9057228056568631, 'rougeLsum': 0.9057095395997856}
0.1535	35.0	8750	0.1750	0.2429	{'bleu': 0.6796704515212395, 'precisions': [0.7946735666277492, 0.7174535809018567, 0.6458425519932419, 0.5795412159641925], 'brevity_penalty': 1.0, 'length_ratio': 1.1194277640409749, 'translation_length': 31691, 'reference_length': 28310}	{'rouge1': 0.9043810437315959, 'rouge2': 0.8363436916820843, 'rougeL': 0.9040836077941827, 'rougeLsum': 0.9040025464797321}
0.1479	36.0	9000	0.1699	0.2363	{'bleu': 0.6857075281147021, 'precisions': [0.7983482016202755, 0.7230720316529481, 0.6528464103491222, 0.5866387337057728], 'brevity_penalty': 1.0, 'length_ratio': 1.1205581066760861, 'translation_length': 31723, 'reference_length': 28310}	{'rouge1': 0.9095427718929339, 'rouge2': 0.8447799177906222, 'rougeL': 0.9092146266329982, 'rougeLsum': 0.9093935335009891}
0.1479	37.0	9250	0.1699	0.2403	{'bleu': 0.6812161709890092, 'precisions': [0.7966445077556189, 0.7194931497125009, 0.6479925680588092, 0.5798004403429053], 'brevity_penalty': 1.0, 'length_ratio': 1.115860120098905, 'translation_length': 31590, 'reference_length': 28310}	{'rouge1': 0.907470542351714, 'rouge2': 0.8409742482167158, 'rougeL': 0.9070243030861842, 'rougeLsum': 0.906984454884277}
0.1468	38.0	9500	0.1705	0.2378	{'bleu': 0.6844362875621229, 'precisions': [0.7981225109046084, 0.7222025370278506, 0.6512940417640893, 0.584556417687202], 'brevity_penalty': 1.0, 'length_ratio': 1.117555634051572, 'translation_length': 31638, 'reference_length': 28310}	{'rouge1': 0.9081373626463022, 'rouge2': 0.8432113124306702, 'rougeL': 0.9078817256970672, 'rougeLsum': 0.907926090518588}
0.1468	39.0	9750	0.1728	0.2357	{'bleu': 0.6872054270890084, 'precisions': [0.8011714421402565, 0.7255848627924314, 0.6537389407344564, 0.5868516002061759], 'brevity_penalty': 1.0, 'length_ratio': 1.1156835040621689, 'translation_length': 31585, 'reference_length': 28310}	{'rouge1': 0.909992727207166, 'rouge2': 0.8454991257092774, 'rougeL': 0.9096844382094951, 'rougeLsum': 0.9096582389858623}
0.1399	40.0	10000	0.1723	0.2360	{'bleu': 0.6873256856440819, 'precisions': [0.8006531802904433, 0.7254818291728895, 0.6542945033595078, 0.5872270486029585], 'brevity_penalty': 1.0, 'length_ratio': 1.1140233133168491, 'translation_length': 31538, 'reference_length': 28310}	{'rouge1': 0.9092508952591971, 'rouge2': 0.8456412258828068, 'rougeL': 0.9089776607080162, 'rougeLsum': 0.9090823488243367}
0.1399	41.0	10250	0.1672	0.2346	{'bleu': 0.6877472473343744, 'precisions': [0.8009430678186018, 0.7262534151793635, 0.6545403157427222, 0.5876100393332084], 'brevity_penalty': 1.0, 'length_ratio': 1.11617802896503, 'translation_length': 31599, 'reference_length': 28310}	{'rouge1': 0.9117540265946094, 'rouge2': 0.8485160184362044, 'rougeL': 0.9114761999726984, 'rougeLsum': 0.9115384496313579}
0.1358	42.0	10500	0.1672	0.2355	{'bleu': 0.6883611823862184, 'precisions': [0.8006038455426665, 0.7259438839174303, 0.6556651646165713, 0.5891998869098106], 'brevity_penalty': 1.0, 'length_ratio': 1.1114447191805017, 'translation_length': 31465, 'reference_length': 28310}	{'rouge1': 0.9103644942076321, 'rouge2': 0.8465167053007057, 'rougeL': 0.9101696238861534, 'rougeLsum': 0.9102477724384457}
0.1358	43.0	10750	0.1680	0.2334	{'bleu': 0.691355440515297, 'precisions': [0.8009272400416312, 0.7272277402707575, 0.6592160804020101, 0.5949962728289229], 'brevity_penalty': 1.0, 'length_ratio': 1.1199929353585305, 'translation_length': 31707, 'reference_length': 28310}	{'rouge1': 0.9117137211829257, 'rouge2': 0.8472381005354184, 'rougeL': 0.9112846690698126, 'rougeLsum': 0.9114123170757924}
0.1316	44.0	11000	0.1701	0.2329	{'bleu': 0.690215899860909, 'precisions': [0.8024052271077302, 0.7284981425791615, 0.6575314902008129, 0.590474413397397], 'brevity_penalty': 1.0, 'length_ratio': 1.1190745319675026, 'translation_length': 31681, 'reference_length': 28310}	{'rouge1': 0.9134133762936256, 'rouge2': 0.8506220034350286, 'rougeL': 0.9129875841880349, 'rougeLsum': 0.9130792687959912}
0.1316	45.0	11250	0.1677	0.2314	{'bleu': 0.6936690640769793, 'precisions': [0.8044002028911996, 0.732259670079636, 0.6616218841048883, 0.5941035632129947], 'brevity_penalty': 1.0, 'length_ratio': 1.1142352525609325, 'translation_length': 31544, 'reference_length': 28310}	{'rouge1': 0.9146221313099991, 'rouge2': 0.854627819059903, 'rougeL': 0.9144106693831648, 'rougeLsum': 0.9144972207187079}
0.125	46.0	11500	0.1712	0.2322	{'bleu': 0.6921327287197928, 'precisions': [0.8030418010497692, 0.7302729528535981, 0.6598773896910543, 0.593022168178842], 'brevity_penalty': 1.0, 'length_ratio': 1.117131755563405, 'translation_length': 31626, 'reference_length': 28310}	{'rouge1': 0.9134976895995741, 'rouge2': 0.8524849207535254, 'rougeL': 0.9132953385707354, 'rougeLsum': 0.9133495371403084}
0.125	47.0	11750	0.1682	0.2329	{'bleu': 0.6919293386914437, 'precisions': [0.802726467611336, 0.7292198581560284, 0.6596191091026469, 0.5936461891171104], 'brevity_penalty': 1.0, 'length_ratio': 1.1167785234899328, 'translation_length': 31616, 'reference_length': 28310}	{'rouge1': 0.9134292267458031, 'rouge2': 0.8516682775912385, 'rougeL': 0.9131191136604613, 'rougeLsum': 0.9131649187010484}
0.1228	48.0	12000	0.1720	0.2308	{'bleu': 0.6938657905892188, 'precisions': [0.8037359586015398, 0.7309378978639128, 0.6617055510860821, 0.5962703962703962], 'brevity_penalty': 1.0, 'length_ratio': 1.1194630872483222, 'translation_length': 31692, 'reference_length': 28310}	{'rouge1': 0.9142754255488477, 'rouge2': 0.8522939134610514, 'rougeL': 0.91378427347294, 'rougeLsum': 0.913791785124439}
0.1228	49.0	12250	0.1675	0.2297	{'bleu': 0.695393888743298, 'precisions': [0.8042468480424685, 0.7321030073323651, 0.6635502720128954, 0.5985329844888806], 'brevity_penalty': 1.0, 'length_ratio': 1.117873542917697, 'translation_length': 31647, 'reference_length': 28310}	{'rouge1': 0.915560398704055, 'rouge2': 0.8541701107254622, 'rougeL': 0.915163858076119, 'rougeLsum': 0.9151431225254174}
0.1191	50.0	12500	0.1667	0.2310	{'bleu': 0.6932836588007911, 'precisions': [0.8033810635211001, 0.7305761753269706, 0.6613331189193535, 0.5951637702091972], 'brevity_penalty': 1.0, 'length_ratio': 1.1199576121511834, 'translation_length': 31706, 'reference_length': 28310}	{'rouge1': 0.9155025168366151, 'rouge2': 0.8541082968528653, 'rougeL': 0.9152005878974918, 'rougeLsum': 0.915366625155241}
0.1191	51.0	12750	0.1641	0.2288	{'bleu': 0.6956956169575305, 'precisions': [0.805068410907827, 0.7327406043002374, 0.6639129558734637, 0.598112502336012], 'brevity_penalty': 1.0, 'length_ratio': 1.117873542917697, 'translation_length': 31647, 'reference_length': 28310}	{'rouge1': 0.916751329399486, 'rouge2': 0.8561752296334002, 'rougeL': 0.916289297513845, 'rougeLsum': 0.9164410215917672}
0.1166	52.0	13000	0.1673	0.2307	{'bleu': 0.6954800243226396, 'precisions': [0.803839838322597, 0.7316296191420076, 0.6637944918666452, 0.5992998833138856], 'brevity_penalty': 1.0, 'length_ratio': 1.1186153302719888, 'translation_length': 31668, 'reference_length': 28310}	{'rouge1': 0.9148182904921852, 'rouge2': 0.853634476747297, 'rougeL': 0.9142736007712273, 'rougeLsum': 0.9144878223020056}
0.1166	53.0	13250	0.1653	0.2283	{'bleu': 0.6957538257225093, 'precisions': [0.8055941406743276, 0.7330148619957537, 0.6637819996779907, 0.5978164512667382], 'brevity_penalty': 1.0, 'length_ratio': 1.1188979159307666, 'translation_length': 31676, 'reference_length': 28310}	{'rouge1': 0.9170466156268146, 'rouge2': 0.8560905896847362, 'rougeL': 0.9166091593124875, 'rougeLsum': 0.9167566551169131}
0.1132	54.0	13500	0.1623	0.2283	{'bleu': 0.6971893080988518, 'precisions': [0.8059677878682403, 0.73399084684429, 0.6653344636873764, 0.6002808988764045], 'brevity_penalty': 1.0, 'length_ratio': 1.116319321794419, 'translation_length': 31603, 'reference_length': 28310}	{'rouge1': 0.9175452778587116, 'rouge2': 0.8575480061603639, 'rougeL': 0.9172218816167347, 'rougeLsum': 0.9172540131018688}
0.1132	55.0	13750	0.1667	0.2293	{'bleu': 0.6975980739177902, 'precisions': [0.8057399329919717, 0.734072709233931, 0.6661291622994436, 0.6010750175274597], 'brevity_penalty': 1.0, 'length_ratio': 1.117555634051572, 'translation_length': 31638, 'reference_length': 28310}	{'rouge1': 0.9171777821964284, 'rouge2': 0.8572916924596359, 'rougeL': 0.9167467076983626, 'rougeLsum': 0.9168313215338679}
0.1101	56.0	14000	0.1704	0.2278	{'bleu': 0.698611601241713, 'precisions': [0.8065433854907539, 0.735355611467451, 0.6671773575777123, 0.6019726078623849], 'brevity_penalty': 1.0, 'length_ratio': 1.1174496644295302, 'translation_length': 31635, 'reference_length': 28310}	{'rouge1': 0.9183634586202567, 'rouge2': 0.8595395157478382, 'rougeL': 0.9182920654950337, 'rougeLsum': 0.9182373756073742}
0.1101	57.0	14250	0.1684	0.2279	{'bleu': 0.6980651688568622, 'precisions': [0.8069325735992403, 0.7350393980265493, 0.6667339849745537, 0.6004590809012976], 'brevity_penalty': 1.0, 'length_ratio': 1.115860120098905, 'translation_length': 31590, 'reference_length': 28310}	{'rouge1': 0.9187291385295998, 'rouge2': 0.8587807295406684, 'rougeL': 0.9183156716145099, 'rougeLsum': 0.9184362361959191}
0.1072	58.0	14500	0.1667	0.2259	{'bleu': 0.7016561795652505, 'precisions': [0.8081824490568419, 0.7380683023403805, 0.6708484117410535, 0.605713220560138], 'brevity_penalty': 1.0, 'length_ratio': 1.1198163193217945, 'translation_length': 31702, 'reference_length': 28310}	{'rouge1': 0.9209465213548746, 'rouge2': 0.8633405489736914, 'rougeL': 0.920716491181567, 'rougeLsum': 0.9208754940401405}
0.1072	59.0	14750	0.1671	0.2260	{'bleu': 0.7010335625872076, 'precisions': [0.807030807030807, 0.7367454994705259, 0.6701452998314201, 0.6061479793517184], 'brevity_penalty': 1.0, 'length_ratio': 1.1213705404450725, 'translation_length': 31746, 'reference_length': 28310}	{'rouge1': 0.9189104710827405, 'rouge2': 0.8608755606605824, 'rougeL': 0.9187382157550807, 'rougeLsum': 0.9186599667158437}
0.1041	60.0	15000	0.1705	0.2260	{'bleu': 0.7004783913084915, 'precisions': [0.8071336295175977, 0.7369090074503019, 0.6694639630596266, 0.6046338513073416], 'brevity_penalty': 1.0, 'length_ratio': 1.1210526315789473, 'translation_length': 31737, 'reference_length': 28310}	{'rouge1': 0.9200124722605665, 'rouge2': 0.8617854846363244, 'rougeL': 0.9196852481683443, 'rougeLsum': 0.9196781172444772}
0.1041	61.0	15250	0.1653	0.2242	{'bleu': 0.7044141994867981, 'precisions': [0.8094096115616422, 0.7400176834659593, 0.6739611408343055, 0.6099118840039163], 'brevity_penalty': 1.0, 'length_ratio': 1.1194277640409749, 'translation_length': 31691, 'reference_length': 28310}	{'rouge1': 0.9217144386541566, 'rouge2': 0.8649468461669139, 'rougeL': 0.9212884367791949, 'rougeLsum': 0.9213364646798634}
0.1004	62.0	15500	0.1668	0.2241	{'bleu': 0.7045613662004655, 'precisions': [0.8100353892821032, 0.7405780674412015, 0.6741215344938749, 0.6093436113057696], 'brevity_penalty': 1.0, 'length_ratio': 1.1179088661250443, 'translation_length': 31648, 'reference_length': 28310}	{'rouge1': 0.9220778457519192, 'rouge2': 0.8653302441431383, 'rougeL': 0.9216515785724653, 'rougeLsum': 0.9216647311088149}
0.1004	63.0	15750	0.1679	0.2249	{'bleu': 0.7051186472128546, 'precisions': [0.8095629365104446, 0.7408155312289652, 0.6749828705009875, 0.6106542056074766], 'brevity_penalty': 1.0, 'length_ratio': 1.117732250088308, 'translation_length': 31643, 'reference_length': 28310}	{'rouge1': 0.9213853170704294, 'rouge2': 0.8651333793191416, 'rougeL': 0.9210709640182315, 'rougeLsum': 0.9211209701199694}
0.0952	64.0	16000	0.1704	0.2259	{'bleu': 0.7005323983436218, 'precisions': [0.8080836809505751, 0.7373529828539039, 0.669555054006126, 0.6036633802158777], 'brevity_penalty': 1.0, 'length_ratio': 1.1177675732956553, 'translation_length': 31644, 'reference_length': 28310}	{'rouge1': 0.920210559153061, 'rouge2': 0.8623975149689453, 'rougeL': 0.9197691946569866, 'rougeLsum': 0.9199395967770367}
0.0952	65.0	16250	0.1672	0.2241	{'bleu': 0.7060033377987773, 'precisions': [0.8103219277718045, 0.7416507126143373, 0.6757966922146027, 0.6117217830581412], 'brevity_penalty': 1.0, 'length_ratio': 1.1169904627340161, 'translation_length': 31622, 'reference_length': 28310}	{'rouge1': 0.921902831041014, 'rouge2': 0.866202812195918, 'rougeL': 0.9216396579521835, 'rougeLsum': 0.9217682869783637}
0.0957	66.0	16500	0.1722	0.2228	{'bleu': 0.7064654921544843, 'precisions': [0.8104661806015845, 0.7417837053808328, 0.6763108124421553, 0.6126399253731343], 'brevity_penalty': 1.0, 'length_ratio': 1.119145178382197, 'translation_length': 31683, 'reference_length': 28310}	{'rouge1': 0.9219434308511755, 'rouge2': 0.8656318720857975, 'rougeL': 0.9215460814670394, 'rougeLsum': 0.9216428260060543}
0.0957	67.0	16750	0.1675	0.2249	{'bleu': 0.7051057423129187, 'precisions': [0.8102185151121118, 0.7410634892406189, 0.6747641604923276, 0.61010898158587], 'brevity_penalty': 1.0, 'length_ratio': 1.1137760508654186, 'translation_length': 31531, 'reference_length': 28310}	{'rouge1': 0.9203795692297823, 'rouge2': 0.8632681126226148, 'rougeL': 0.9201400984459089, 'rougeLsum': 0.9201320100889545}
0.0941	68.0	17000	0.1682	0.2227	{'bleu': 0.7076222719778471, 'precisions': [0.8112235219728107, 0.7429290423194159, 0.6775949673360755, 0.6139711039416468], 'brevity_penalty': 1.0, 'length_ratio': 1.117273048392794, 'translation_length': 31630, 'reference_length': 28310}	{'rouge1': 0.9230846878776521, 'rouge2': 0.8675318080450498, 'rougeL': 0.9228049915850105, 'rougeLsum': 0.9227780467865668}
0.0941	69.0	17250	0.1685	0.2220	{'bleu': 0.7091569326556427, 'precisions': [0.812025556680162, 0.744113475177305, 0.67890574564235, 0.6165255228559398], 'brevity_penalty': 1.0, 'length_ratio': 1.1167785234899328, 'translation_length': 31616, 'reference_length': 28310}	{'rouge1': 0.9226701085514796, 'rouge2': 0.867217116394777, 'rougeL': 0.9224081952300498, 'rougeLsum': 0.9223496600457706}
0.0906	70.0	17500	0.1698	0.2246	{'bleu': 0.7044658387712242, 'precisions': [0.8098930312045066, 0.7405081257540274, 0.6740692885407413, 0.6092250058534301], 'brevity_penalty': 1.0, 'length_ratio': 1.1161427057576827, 'translation_length': 31598, 'reference_length': 28310}	{'rouge1': 0.921670926824965, 'rouge2': 0.8649207078216781, 'rougeL': 0.9213491025074665, 'rougeLsum': 0.9214347837843797}
0.0906	71.0	17750	0.1702	0.2217	{'bleu': 0.7084662509608048, 'precisions': [0.8110641252209038, 0.7431380871533673, 0.6789507563566141, 0.6156213569596642], 'brevity_penalty': 1.0, 'length_ratio': 1.1193217944189333, 'translation_length': 31688, 'reference_length': 28310}	{'rouge1': 0.923372397595406, 'rouge2': 0.8683184508980024, 'rougeL': 0.923005410812489, 'rougeLsum': 0.9229948346659644}
0.0889	72.0	18000	0.1702	0.2208	{'bleu': 0.7103922504377193, 'precisions': [0.8125868823455074, 0.7453959484346224, 0.6807413376309428, 0.617666292974589], 'brevity_penalty': 1.0, 'length_ratio': 1.1180501589544332, 'translation_length': 31652, 'reference_length': 28310}	{'rouge1': 0.9237938487200171, 'rouge2': 0.8691894176907089, 'rougeL': 0.9234306305070279, 'rougeLsum': 0.9235362071403326}
0.0889	73.0	18250	0.1688	0.2210	{'bleu': 0.7075558148047492, 'precisions': [0.8117049149278702, 0.7432685843682553, 0.6774258461786131, 0.6132493585257756], 'brevity_penalty': 1.0, 'length_ratio': 1.1190038855528082, 'translation_length': 31679, 'reference_length': 28310}	{'rouge1': 0.9235870670238353, 'rouge2': 0.867731941498739, 'rougeL': 0.9231963614143748, 'rougeLsum': 0.9231174606077445}
0.0873	74.0	18500	0.1687	0.2201	{'bleu': 0.7111541525608382, 'precisions': [0.8126618250710451, 0.745876690026191, 0.6817779209276109, 0.6189209371791282], 'brevity_penalty': 1.0, 'length_ratio': 1.1186859766866832, 'translation_length': 31670, 'reference_length': 28310}	{'rouge1': 0.9241524377364316, 'rouge2': 0.8701741142370556, 'rougeL': 0.9237664232694494, 'rougeLsum': 0.9237557469048323}
0.0873	75.0	18750	0.1693	0.2196	{'bleu': 0.7101122997387354, 'precisions': [0.8133594663800462, 0.74529538930432, 0.6804161122535382, 0.616485109168264], 'brevity_penalty': 1.0, 'length_ratio': 1.1173790180148357, 'translation_length': 31633, 'reference_length': 28310}	{'rouge1': 0.9246930686869193, 'rouge2': 0.8697208230362767, 'rougeL': 0.9242964590840115, 'rougeLsum': 0.924353328742542}
0.0871	76.0	19000	0.1714	0.2191	{'bleu': 0.7100726095800501, 'precisions': [0.8131642854890088, 0.7450425930507936, 0.6803618090452261, 0.6167536339918003], 'brevity_penalty': 1.0, 'length_ratio': 1.1199929353585305, 'translation_length': 31707, 'reference_length': 28310}	{'rouge1': 0.9246913936765786, 'rouge2': 0.8698103105720247, 'rougeL': 0.9242785961704064, 'rougeLsum': 0.9242973577312759}
0.0871	77.0	19250	0.1713	0.2204	{'bleu': 0.71039613732396, 'precisions': [0.8124506988924999, 0.7447749054001486, 0.68066449458992, 0.6183682983682983], 'brevity_penalty': 1.0, 'length_ratio': 1.1194984104556693, 'translation_length': 31693, 'reference_length': 28310}	{'rouge1': 0.9235755205534675, 'rouge2': 0.8684411156089031, 'rougeL': 0.9231019715362735, 'rougeLsum': 0.9232179338752297}
0.0849	78.0	19500	0.1702	0.2200	{'bleu': 0.7113022330890457, 'precisions': [0.8126972106525306, 0.7456500212194087, 0.6819388576025744, 0.6194516971279374], 'brevity_penalty': 1.0, 'length_ratio': 1.1194630872483222, 'translation_length': 31692, 'reference_length': 28310}	{'rouge1': 0.9249026504809992, 'rouge2': 0.8706738634899978, 'rougeL': 0.9244228213593967, 'rougeLsum': 0.9245163954979058}
0.0849	79.0	19750	0.1721	0.2191	{'bleu': 0.7129126662447548, 'precisions': [0.8140130206687314, 0.7472897328704031, 0.6839177750906892, 0.6208991494532199], 'brevity_penalty': 1.0, 'length_ratio': 1.117696926880961, 'translation_length': 31642, 'reference_length': 28310}	{'rouge1': 0.9258933535321777, 'rouge2': 0.8725241424848458, 'rougeL': 0.925407277157843, 'rougeLsum': 0.9255103156408372}
0.0815	80.0	20000	0.1731	0.2197	{'bleu': 0.7130494687043093, 'precisions': [0.8131840403721811, 0.746933437024992, 0.6839142845655932, 0.6223091976516634], 'brevity_penalty': 1.0, 'length_ratio': 1.119922288943836, 'translation_length': 31705, 'reference_length': 28310}	{'rouge1': 0.9249734482469991, 'rouge2': 0.8714582527236612, 'rougeL': 0.9245264875688315, 'rougeLsum': 0.9247533582142475}
0.0815	81.0	20250	0.1676	0.2183	{'bleu': 0.7126549142600589, 'precisions': [0.8138427079718603, 0.7471626065127461, 0.6835163067519202, 0.6206012584479143], 'brevity_penalty': 1.0, 'length_ratio': 1.1197103496997527, 'translation_length': 31699, 'reference_length': 28310}	{'rouge1': 0.9260595942273723, 'rouge2': 0.8718019409896021, 'rougeL': 0.925615538503286, 'rougeLsum': 0.9257780718641335}
0.0828	82.0	20500	0.1707	0.2182	{'bleu': 0.7139305442316648, 'precisions': [0.8142121394040885, 0.74806077993837, 0.6850143047104807, 0.6226582574164915], 'brevity_penalty': 1.0, 'length_ratio': 1.1179441893323914, 'translation_length': 31649, 'reference_length': 28310}	{'rouge1': 0.9258408326071554, 'rouge2': 0.8723610323392393, 'rougeL': 0.9254465900530321, 'rougeLsum': 0.9254541563635914}
0.0828	83.0	20750	0.1704	0.2184	{'bleu': 0.7126769859245141, 'precisions': [0.8142482379341951, 0.7476526237465897, 0.6833151932922159, 0.6201448936667445], 'brevity_penalty': 1.0, 'length_ratio': 1.117590957258919, 'translation_length': 31639, 'reference_length': 28310}	{'rouge1': 0.9252233056810141, 'rouge2': 0.8708633237488795, 'rougeL': 0.9248945519512725, 'rougeLsum': 0.9249737040933624}
0.0799	84.0	21000	0.1735	0.2170	{'bleu': 0.7142609248316687, 'precisions': [0.8148405431007263, 0.748672754300276, 0.6852806184072792, 0.6225789891258692], 'brevity_penalty': 1.0, 'length_ratio': 1.1186859766866832, 'translation_length': 31670, 'reference_length': 28310}	{'rouge1': 0.9261235872875397, 'rouge2': 0.872145885894907, 'rougeL': 0.9256949358727219, 'rougeLsum': 0.9258287208627041}
0.0799	85.0	21250	0.1721	0.2168	{'bleu': 0.7158739847138782, 'precisions': [0.815227689003979, 0.7498407079646018, 0.6870419586051382, 0.625338437120717], 'brevity_penalty': 1.0, 'length_ratio': 1.1185446838572943, 'translation_length': 31666, 'reference_length': 28310}	{'rouge1': 0.9269207859875149, 'rouge2': 0.8735723624582992, 'rougeL': 0.9265515137657597, 'rougeLsum': 0.9265853633726688}
0.0778	86.0	21500	0.1668	0.2169	{'bleu': 0.7155603590564118, 'precisions': [0.8149433628877039, 0.7495844679421438, 0.6868187120389365, 0.624877616672106], 'brevity_penalty': 1.0, 'length_ratio': 1.1194984104556693, 'translation_length': 31693, 'reference_length': 28310}	{'rouge1': 0.9271266500391548, 'rouge2': 0.8738241771944291, 'rougeL': 0.9266902262285294, 'rougeLsum': 0.9268494860994518}
0.0778	87.0	21750	0.1710	0.2177	{'bleu': 0.714363823025843, 'precisions': [0.814993839446498, 0.748911003293551, 0.6852665081987027, 0.6226353402774534], 'brevity_penalty': 1.0, 'length_ratio': 1.1180854821617803, 'translation_length': 31653, 'reference_length': 28310}	{'rouge1': 0.9266358627816298, 'rouge2': 0.8731572473513698, 'rougeL': 0.926130725682236, 'rougeLsum': 0.9263381022337849}
0.0758	88.0	22000	0.1702	0.2174	{'bleu': 0.7144227231583102, 'precisions': [0.8149423471805401, 0.7486100782605616, 0.6854127220722717, 0.6229975246368689], 'brevity_penalty': 1.0, 'length_ratio': 1.1181561285764747, 'translation_length': 31655, 'reference_length': 28310}	{'rouge1': 0.9267706479518243, 'rouge2': 0.8731114589996107, 'rougeL': 0.9263773943377853, 'rougeLsum': 0.9264959189034179}
0.0758	89.0	22250	0.1696	0.2170	{'bleu': 0.7153554251271139, 'precisions': [0.8158509630565204, 0.7496637644227366, 0.6864079233432644, 0.6237748529823579], 'brevity_penalty': 1.0, 'length_ratio': 1.1186859766866832, 'translation_length': 31670, 'reference_length': 28310}	{'rouge1': 0.927575406821849, 'rouge2': 0.875133469594803, 'rougeL': 0.9270927956435113, 'rougeLsum': 0.9271444283570649}
0.0754	90.0	22500	0.1701	0.2158	{'bleu': 0.7166564120885003, 'precisions': [0.8162421487864154, 0.750769448473485, 0.6878596434751116, 0.6257754559447736], 'brevity_penalty': 1.0, 'length_ratio': 1.119145178382197, 'translation_length': 31683, 'reference_length': 28310}	{'rouge1': 0.9278769278873709, 'rouge2': 0.875847033569106, 'rougeL': 0.9273847252800362, 'rougeLsum': 0.9275403837016275}
0.0754	91.0	22750	0.1713	0.2153	{'bleu': 0.7173473624867931, 'precisions': [0.8167514454519604, 0.7515140782716486, 0.6884241911438818, 0.6266641752697716], 'brevity_penalty': 1.0, 'length_ratio': 1.1180148357470858, 'translation_length': 31651, 'reference_length': 28310}	{'rouge1': 0.9288327108695038, 'rouge2': 0.8770902993358441, 'rougeL': 0.9284266054226216, 'rougeLsum': 0.9286241132627304}
0.0707	92.0	23000	0.1694	0.2155	{'bleu': 0.7171809451577761, 'precisions': [0.8170002846029788, 0.751338320275109, 0.6882739703924812, 0.6261752186725291], 'brevity_penalty': 1.0, 'length_ratio': 1.1170257859413635, 'translation_length': 31623, 'reference_length': 28310}	{'rouge1': 0.9276431790642398, 'rouge2': 0.8749354749956386, 'rougeL': 0.9273036622670998, 'rougeLsum': 0.9273863508775859}
0.0707	93.0	23250	0.1714	0.2160	{'bleu': 0.7164521046051908, 'precisions': [0.8162227067336556, 0.7506641635082002, 0.6873665121902075, 0.625613231789936], 'brevity_penalty': 1.0, 'length_ratio': 1.117873542917697, 'translation_length': 31647, 'reference_length': 28310}	{'rouge1': 0.927975935364792, 'rouge2': 0.8758224471806314, 'rougeL': 0.9275528355153535, 'rougeLsum': 0.9276874737924827}
0.0734	94.0	23500	0.1709	0.2149	{'bleu': 0.7177211593064339, 'precisions': [0.8169938766492014, 0.7520696242835916, 0.6890140845070423, 0.626784214945424], 'brevity_penalty': 1.0, 'length_ratio': 1.11910985517485, 'translation_length': 31682, 'reference_length': 28310}	{'rouge1': 0.9291048922590844, 'rouge2': 0.8776047364139292, 'rougeL': 0.9287323594925806, 'rougeLsum': 0.9287543024329734}
0.0734	95.0	23750	0.1696	0.2155	{'bleu': 0.7170068841937269, 'precisions': [0.8167208663530452, 0.7513890363449764, 0.6880157803631094, 0.625974147183723], 'brevity_penalty': 1.0, 'length_ratio': 1.1187919463087248, 'translation_length': 31673, 'reference_length': 28310}	{'rouge1': 0.9283940026586062, 'rouge2': 0.8762847686551375, 'rougeL': 0.9280054629066815, 'rougeLsum': 0.9281065331235923}
0.0719	96.0	24000	0.1720	0.2155	{'bleu': 0.7170633786928619, 'precisions': [0.8164830655597992, 0.7512117459755882, 0.6882369511851584, 0.6263003218733965], 'brevity_penalty': 1.0, 'length_ratio': 1.1190745319675026, 'translation_length': 31681, 'reference_length': 28310}	{'rouge1': 0.9286091912806647, 'rouge2': 0.8766398698986719, 'rougeL': 0.9281196299111021, 'rougeLsum': 0.9281658142488232}
0.0719	97.0	24250	0.1702	0.2149	{'bleu': 0.7187612866004341, 'precisions': [0.8172542330048016, 0.752584985835694, 0.6901788591685466, 0.628730210619717], 'brevity_penalty': 1.0, 'length_ratio': 1.118191451783822, 'translation_length': 31656, 'reference_length': 28310}	{'rouge1': 0.9291479210163982, 'rouge2': 0.8780469541560687, 'rougeL': 0.9286163775686974, 'rougeLsum': 0.9287525750830166}
0.0706	98.0	24500	0.1707	0.2154	{'bleu': 0.7178571185129792, 'precisions': [0.8168298073886959, 0.7518581439796135, 0.6892261856832274, 0.6273686175674414], 'brevity_penalty': 1.0, 'length_ratio': 1.1186859766866832, 'translation_length': 31670, 'reference_length': 28310}	{'rouge1': 0.9288819464777023, 'rouge2': 0.8771859245310464, 'rougeL': 0.9283519465459722, 'rougeLsum': 0.9284754797160513}
0.0706	99.0	24750	0.1711	0.2152	{'bleu': 0.7178888345161291, 'precisions': [0.8170157646984488, 0.7518149945107483, 0.6890939124128762, 0.6274931103741417], 'brevity_penalty': 1.0, 'length_ratio': 1.1180854821617803, 'translation_length': 31653, 'reference_length': 28310}	{'rouge1': 0.9288584007055651, 'rouge2': 0.8767258745591503, 'rougeL': 0.9284019306689311, 'rougeLsum': 0.9284844443050899}
0.0706	99.6021	24900	0.1710	0.2150	{'bleu': 0.7181439137868495, 'precisions': [0.8172253641275157, 0.7521161678767487, 0.6893509005197631, 0.627738590180782], 'brevity_penalty': 1.0, 'length_ratio': 1.1180148357470858, 'translation_length': 31651, 'reference_length': 28310}	{'rouge1': 0.9290507331814231, 'rouge2': 0.877068996182836, 'rougeL': 0.928568135242265, 'rougeLsum': 0.9287057494850774}

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0